EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

EvoAgent-SQL: An Evolutionary Multi-Agent Text2SQL Framework Integrating User Feedback and Reflective Adaptation

Bin He, Yanshu Du, Hao Meng, Shengbing Tang, Ting Zhang, Longfei Song

Symmetry · 06.05.2026 · 18 (5) · 792

DOI: 10.3390/sym18050792 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Symmetry, online erschienen am 06.05.2026. Verfasst von Bin He und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Natural language to structured query language (Text2SQL) is a critical task in intelligent question answering and database interaction. A fundamental challenge lies in achieving semantic symmetry between natural language expressions and database schemas, as well as behavioral symmetry between query generation and error correction. Traditional approaches often struggle with comprehending domain-specific concepts and dynamically adapting to user’s feedback, breaking the desired symmetry between system output and user intent. Thispaper presents EvoAgent-SQL as a lightweight engineering framework for private domain data querying based on low-cost lightweight models. The framework comprises three core agents: (1) the Schema Grounding Agent (SGA) establishes a symmetric mapping from natural language concepts to database fields; (2) the Execution Agent (EA) generates SQL queries; and (3) the Reflection Agent (RA) mirrors the EA’s outputs by analyzing errors and proposing corrections, forming a reflective symmetry loop. When ambiguity arises, user feedback is incorporated as a symmetry-breaking signal, which the RA uses to restore alignment through iterative evolution with a memory mechanism. We evaluate the framework on an education-domain dataset and provide a reproducibility plan for releasing sanitized schemas, natural language questions, and reference SQL while withholding confidential institutional records. Experimental results demonstrate that EvoAgent-SQL enhances query execution accuracy, achieving a 13.7% reduction in the relative error residual after one evolution cycle and a 17.6% cumulative reduction after two cycles, suggesting practical adaptability in domain-specific Text2SQL tasks.

Förderung

  • National Natural Science Foundation of China
  • Fundamental Research Funds for the Central Universities

Zitieren

APA

He, B., Du, Y., Meng, H., Tang, S., Zhang, T., & Song, L. (2026). EvoAgent-SQL: An Evolutionary Multi-Agent Text2SQL Framework Integrating User Feedback and Reflective Adaptation. Symmetry, 18(5), 792. https://doi.org/10.3390/sym18050792

Vancouver

He B, Du Y, Meng H, Tang S, Zhang T, Song L. EvoAgent-SQL: An Evolutionary Multi-Agent Text2SQL Framework Integrating User Feedback and Reflective Adaptation. Symmetry. 2026;18(5):792. doi:10.3390/sym18050792

BibTeX
@article{He2026,
  author = {He, Bin and Du, Yanshu and Meng, Hao and Tang, Shengbing and Zhang, Ting and Song, Longfei},
  title = {EvoAgent-SQL: An Evolutionary Multi-Agent Text2SQL Framework Integrating User Feedback and Reflective Adaptation},
  journal = {Symmetry},
  year = {2026},
  volume = {18},
  number = {5},
  pages = {792},
  doi = {10.3390/sym18050792}
}
Kostenlos starten →